← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
16k
tokens
3,722
PP tok/s
84.1
TG tok/s
4401
TTFT (ms)
37.5
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.5.1
macOS
macOS 27.0
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 3,237 | 89.0 | 35.4 GB | view |
| 4k | 4,216 | 88.3 | 36.2 GB | view |
| 8k | 4,034 | 85.8 | 36.6 GB | view |
| 16k | 3,722 | 84.1 | 37.5 GB | current |
| 32k | 3,217 | 75.2 | 39.3 GB | view |
| 64k | 2,242 | 68.5 | 42.0 GB | view |
| 128k | 1,398 | 57.9 | 48.0 GB | view |
| 195k | 984.9 | 45.2 | 54.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 89.0 | 1.00× |
| 2× | 156.7 | 1.76× |
| 4× | 248.2 | 2.79× |
| 8× | 321.7 | 3.61× |